Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning model

The term “invasive noxious weed species” (INWS), which refers to noxious weed plants that invade native alpine grasslands, has increasingly become an ecological and economic threat in the alpine grassland ecosystem of the Qinghai-Tibetan Plateau (QTP). Both the INWS and native grass species are smal...

Full description

Saved in:
Bibliographic Details
Main Authors: Fei Xing, Ru An, Xulin Guo, Xiaoji Shen
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:GIScience & Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/15481603.2024.2327146
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850245244546711552
author Fei Xing
Ru An
Xulin Guo
Xiaoji Shen
author_facet Fei Xing
Ru An
Xulin Guo
Xiaoji Shen
author_sort Fei Xing
collection DOAJ
description The term “invasive noxious weed species” (INWS), which refers to noxious weed plants that invade native alpine grasslands, has increasingly become an ecological and economic threat in the alpine grassland ecosystem of the Qinghai-Tibetan Plateau (QTP). Both the INWS and native grass species are small in physical size and share a habitat. Using remote sensing data to distinguish INWS from native alpine grass species remains a challenge. High spatial resolution hyperspectral imagery provides an alternative for addressing this problem. Here, we explored the use of unmanned aerial vehicle (UAV) hyperspectral imagery and deep learning methods with a small sample size for mapping the INWS in mixed alpine grasslands. To assess the method, UAV hyperspectral data with a very high spatial resolution of 2 cm were collected from the study site, and a novel convolutional neural network (CNN) model called 3D&2D-INWS-CNN was developed to take full advantage of the rich information provided by the imagery. The results indicate that the proposed 3D&2D-INWS-CNN model applied to the collected imagery for mapping INWS and native species with small ground truth training samples is robust and sufficient, with an overall classification accuracy exceeding 95% and a kappa value of 98.67%. The F1 score for each native species and INWS ranged from 92% to 99%. In conclusion, our results highlight the potential of using very high spatial resolution UAV hyperspectral data combined with a state-of-the-art deep learning model for INWS mapping even with small training samples in degraded alpine grassland ecosystems. Studies such as ours can aid the development of invasive species management practices and provide more data for decision-making in controlling the spread of invasive species in similar grassland ecosystems or, more widely, in terrestrial ecosystems.
format Article
id doaj-art-a29de239e7174d4bbb8e8bc0821e25db
institution OA Journals
issn 1548-1603
1943-7226
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series GIScience & Remote Sensing
spelling doaj-art-a29de239e7174d4bbb8e8bc0821e25db2025-08-20T01:59:30ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262024-12-0161110.1080/15481603.2024.2327146Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning modelFei Xing0Ru An1Xulin Guo2Xiaoji Shen3College of Geography and Remote Sensing, Hohai University, Nanjing, ChinaCollege of Geography and Remote Sensing, Hohai University, Nanjing, ChinaDepartment of Geography and Planning, University of Saskatchewan, Saskatoon, CanadaThe National Key Laboratory of Water Disaster Prevention, Hohai University, Nanjing, ChinaThe term “invasive noxious weed species” (INWS), which refers to noxious weed plants that invade native alpine grasslands, has increasingly become an ecological and economic threat in the alpine grassland ecosystem of the Qinghai-Tibetan Plateau (QTP). Both the INWS and native grass species are small in physical size and share a habitat. Using remote sensing data to distinguish INWS from native alpine grass species remains a challenge. High spatial resolution hyperspectral imagery provides an alternative for addressing this problem. Here, we explored the use of unmanned aerial vehicle (UAV) hyperspectral imagery and deep learning methods with a small sample size for mapping the INWS in mixed alpine grasslands. To assess the method, UAV hyperspectral data with a very high spatial resolution of 2 cm were collected from the study site, and a novel convolutional neural network (CNN) model called 3D&2D-INWS-CNN was developed to take full advantage of the rich information provided by the imagery. The results indicate that the proposed 3D&2D-INWS-CNN model applied to the collected imagery for mapping INWS and native species with small ground truth training samples is robust and sufficient, with an overall classification accuracy exceeding 95% and a kappa value of 98.67%. The F1 score for each native species and INWS ranged from 92% to 99%. In conclusion, our results highlight the potential of using very high spatial resolution UAV hyperspectral data combined with a state-of-the-art deep learning model for INWS mapping even with small training samples in degraded alpine grassland ecosystems. Studies such as ours can aid the development of invasive species management practices and provide more data for decision-making in controlling the spread of invasive species in similar grassland ecosystems or, more widely, in terrestrial ecosystems.https://www.tandfonline.com/doi/10.1080/15481603.2024.2327146Invasive noxious weed species (INWS)very-high spatial resolutionUAV hyperspectral imageryconvolutional neural networksalpine grassland ecosystemQinghai-Tibetan Plateau (QTP)
spellingShingle Fei Xing
Ru An
Xulin Guo
Xiaoji Shen
Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning model
GIScience & Remote Sensing
Invasive noxious weed species (INWS)
very-high spatial resolution
UAV hyperspectral imagery
convolutional neural networks
alpine grassland ecosystem
Qinghai-Tibetan Plateau (QTP)
title Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning model
title_full Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning model
title_fullStr Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning model
title_full_unstemmed Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning model
title_short Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning model
title_sort mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution uav hyperspectral imagery and a novel deep learning model
topic Invasive noxious weed species (INWS)
very-high spatial resolution
UAV hyperspectral imagery
convolutional neural networks
alpine grassland ecosystem
Qinghai-Tibetan Plateau (QTP)
url https://www.tandfonline.com/doi/10.1080/15481603.2024.2327146
work_keys_str_mv AT feixing mappinginvasivenoxiousweedspeciesinthealpinegrasslandecosystemsusingveryhighspatialresolutionuavhyperspectralimageryandanoveldeeplearningmodel
AT ruan mappinginvasivenoxiousweedspeciesinthealpinegrasslandecosystemsusingveryhighspatialresolutionuavhyperspectralimageryandanoveldeeplearningmodel
AT xulinguo mappinginvasivenoxiousweedspeciesinthealpinegrasslandecosystemsusingveryhighspatialresolutionuavhyperspectralimageryandanoveldeeplearningmodel
AT xiaojishen mappinginvasivenoxiousweedspeciesinthealpinegrasslandecosystemsusingveryhighspatialresolutionuavhyperspectralimageryandanoveldeeplearningmodel